Multi-scale attention network (MSAN) for track circuits fault diagnosis
Abstract As one of the three major outdoor components of the railroad signal system, the track circuit plays an important role in ensuring the safety and efficiency of train operation. Therefore, when a fault occurs, the cause of the fault needs to be found quickly and accurately and dealt with in a...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2024-04-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-024-59711-2 |
| _version_ | 1797199375930228736 |
|---|---|
| author | Weijie Tao Xiaowei Li Jianlei Liu Zheng Li |
| author_facet | Weijie Tao Xiaowei Li Jianlei Liu Zheng Li |
| author_sort | Weijie Tao |
| collection | DOAJ |
| description | Abstract As one of the three major outdoor components of the railroad signal system, the track circuit plays an important role in ensuring the safety and efficiency of train operation. Therefore, when a fault occurs, the cause of the fault needs to be found quickly and accurately and dealt with in a timely manner to avoid affecting the efficiency of train operation and the occurrence of safety accidents. This article proposes a fault diagnosis method based on multi-scale attention network, which uses Gramian Angular Field (GAF) to transform one-dimensional time series into two-dimensional images, making full use of the advantages of convolutional networks in processing image data. A new feature fusion training structure is designed to effectively train the model, fully extract features at different scales, and fusing spatial feature information through spatial attention mechanisms. Finally, experiments are conducted using real track circuit fault datasets, and the accuracy of fault diagnosis reaches 99.36%, and our model demonstrates better performance compared to classical and state-of-the-art models. And the ablation experiments verified that each module in the designed model plays a key role. |
| first_indexed | 2024-04-24T07:14:46Z |
| format | Article |
| id | doaj.art-0ab4bcdb83f84feab691ff84b45656bb |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-04-24T07:14:46Z |
| publishDate | 2024-04-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-0ab4bcdb83f84feab691ff84b45656bb2024-04-21T11:18:44ZengNature PortfolioScientific Reports2045-23222024-04-0114111210.1038/s41598-024-59711-2Multi-scale attention network (MSAN) for track circuits fault diagnosisWeijie Tao0Xiaowei Li1Jianlei Liu2Zheng Li3Department of Rail Transportation, Shandong Jiaotong UniversityDepartment of Rail Transportation, Shandong Jiaotong UniversityDepartment of Cyberspace Security, Qufu Normal UniversityDepartment of Rail Transportation, Shandong Jiaotong UniversityAbstract As one of the three major outdoor components of the railroad signal system, the track circuit plays an important role in ensuring the safety and efficiency of train operation. Therefore, when a fault occurs, the cause of the fault needs to be found quickly and accurately and dealt with in a timely manner to avoid affecting the efficiency of train operation and the occurrence of safety accidents. This article proposes a fault diagnosis method based on multi-scale attention network, which uses Gramian Angular Field (GAF) to transform one-dimensional time series into two-dimensional images, making full use of the advantages of convolutional networks in processing image data. A new feature fusion training structure is designed to effectively train the model, fully extract features at different scales, and fusing spatial feature information through spatial attention mechanisms. Finally, experiments are conducted using real track circuit fault datasets, and the accuracy of fault diagnosis reaches 99.36%, and our model demonstrates better performance compared to classical and state-of-the-art models. And the ablation experiments verified that each module in the designed model plays a key role.https://doi.org/10.1038/s41598-024-59711-2Multi-scale neural networkGramian Angular Field (GAF)Spatial attentionFeature fusionFault diagnosis |
| spellingShingle | Weijie Tao Xiaowei Li Jianlei Liu Zheng Li Multi-scale attention network (MSAN) for track circuits fault diagnosis Scientific Reports Multi-scale neural network Gramian Angular Field (GAF) Spatial attention Feature fusion Fault diagnosis |
| title | Multi-scale attention network (MSAN) for track circuits fault diagnosis |
| title_full | Multi-scale attention network (MSAN) for track circuits fault diagnosis |
| title_fullStr | Multi-scale attention network (MSAN) for track circuits fault diagnosis |
| title_full_unstemmed | Multi-scale attention network (MSAN) for track circuits fault diagnosis |
| title_short | Multi-scale attention network (MSAN) for track circuits fault diagnosis |
| title_sort | multi scale attention network msan for track circuits fault diagnosis |
| topic | Multi-scale neural network Gramian Angular Field (GAF) Spatial attention Feature fusion Fault diagnosis |
| url | https://doi.org/10.1038/s41598-024-59711-2 |
| work_keys_str_mv | AT weijietao multiscaleattentionnetworkmsanfortrackcircuitsfaultdiagnosis AT xiaoweili multiscaleattentionnetworkmsanfortrackcircuitsfaultdiagnosis AT jianleiliu multiscaleattentionnetworkmsanfortrackcircuitsfaultdiagnosis AT zhengli multiscaleattentionnetworkmsanfortrackcircuitsfaultdiagnosis |